Dense

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 45

All topics

ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual Density
Sep 30, 2026Xinhe Wu, Yadong JinDense Multimodal Large Language Models
iSoftStone AI Research Lab (ISSAIR) iSoftStone Beijing, China
Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation
Sep 27, 2026Yuhao Sun, Binrui Wu, Zhuoer Xu +5Efficient On-Policy Distillation Teacher
Ant Group · University of Science and Technology of China · Alibaba International Digital Commerce Group +2
Dense Coverage, Sparse Refinement: Byte-Constrained Cooperative Perception
Sep 24, 2026Melih Yazgan, Timon Müller, J. Marius ZöllnerCollaborative Perception V2X
FZI Research Center for Information Technology · Karlsruhe Institute of Technology
Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant
Sep 19, 2026Satyanarayan Pati, Srikanth PatilRetrieval Layer Vector Database
Involead Services Pvt. Ltd.
Training Neural Networks to Approach the Optimum Bayes Estimator in Dense Multi-Emitter Localization
Sep 17, 2026Yi Sun, Mona Sharifi, Muzna YummanNeural Network Training Neural Network
Electrical Engineering Department Applied and Embodied AI Lab The City College of City University of New York New York, NY 10031, USA
Dense to MoE Adaptation for Compact Vision Language Action Policies
Sep 15, 2026Muchun Niu, Shuang Chen, Yuzhou Wu +1Vision-Language Model Adaptation Dense
Shanghai Jiao Tong University, Shanghai, China · Tianji KernalMind Co., Ltd.
Parameter-Efficient Retrievers for Polish and European Languages
Sep 11, 2026Sławomir Dadas, Rafał Poświata, Małgorzata Grębowiec +1Retrieval Layer Retrievers
National Information Processing Institute al. Niepodległości 188b, 00-608 Warsaw, Poland
Routing Dense Layouts with History-Aware Offline Reinforcement Learning using LSTM
Sep 8, 2026Afsara Khan, Austin RovinskiModel-Based Reinforcement Learning Dense
New York University Brooklyn, New York, USA
Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications
Sep 1, 2026S. Sifaoui, E. Angelini, S. Toupin +2Self-Supervised Representations Dense Prediction
LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France · MIRACL.ai Laboratory, Hôpital Universitaire Lariboisière (AP-HP), Paris, France · Université Paris Cité, Inserm MASCOT, Paris, France
Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings
Aug 18, 2026Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon +2Large Language Model Safety Guardrail
Graduate School of Informatics, Osaka Metropolitan University, Osaka 558-8585, Japan · Dept. of Computer Science and Engineering, BRAC University, Dhaka 1212, Bangladesh · Dept. of Chemical Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka 1000, Bangladesh +1
Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors
Aug 16, 2026Chunran ZhangDense
School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu, China
Generative Embedding Benchmark: How Much Information Survives in a Dense Embedding?
Aug 7, 2026Yun Li, Biao Yang, Peixi Wu +5Discriminative Dense
2Fudan University · 1Kuaishou Technology · University of Science and Technology of China +1
Dense-Cast: A lightweight ensemble of deep learning architectures for precipitation nowcasting
Aug 6, 2026Gourav Jyoti Kalita, Hidam Kumarjit SinghPrecipitation Nowcasting Rainfall
Department of Electronics and Communication Technology, Gauhati University, Guwahati-781014, Assam, India
FM4WiFi: Flow Matching for Multi-AP Coordination in Dense Deployments of Beyond Wi-Fi 8 Networks
Aug 4, 2026Maksymilian Wojnar, Krzysztof Rusek, Katarzyna Kosek-Szott +1Wifi Adaptive Coordination
AGH University of Krakow, Poland
UEmbed: Unified Sparse and Dense Multimodal Embeddings
Aug 3, 2026Tingyu Song, Mingxin Li, Yanzhao Zhang +5Multimodal Embeddings Embedder
CASIA · University of Chinese Academy of Sciences · Alibaba Group +1
Sparse Meets Dense: Correspondence Guided Robotic Manipulation with Rigid-Deformable Interactions
Aug 2, 2026Ziyu Zhu, Yue Chen, Xirui Liang +5Deformable Linear Objects Robotic Manipulation
School of EECS, PKU · CFCS, School of Computer Science, PKU
Dense Temporal Contrast Synthesis via Conditioned Latent Transport
Jul 31, 2026Smriti Joshi, Apostolia Tsirikoglou, Daniel M. Lang +15Magnetic Resonance Imaging Adaptive Histogram Equalization
Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain · Department of Oncology-Pathology, Karolinska Institutet, SE-171 77, Stockholm, Sweden · Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Munich, Germany +9
Learning Dense 2D-3D Correspondence for X-ray-to-CT Registration of Knee Bones
Jul 24, 2026Rembert Daems, Jonas Grammens, Caro Roten +3Image Registration Cone-Beam Computed Tomography
Arthro ID · KU Leuven · AZ Delta
Think Sparse, Predict Dense: Continuous Thought Machines for Image Super-Resolution
Jul 21, 2026Zekai ShiDense Thoughts
Xi’an Jiaotong University
DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation
Jul 14, 2026Yu Fang, Wanxi Dong, Jiaqi Liu +7Dense
University of North Carolina at Chapel Hill · Carnegie Mellon University · Shanghai Jiao Tong University +1
Next-Dense-Stride Prediction for Multimodal Autoregressive Visual Modeling
Jul 10, 2026Chicago Y. Park, Jialin Mao, Xiaojian Xu +3Autoregressive Image Generation Dense Prediction
University of Wisconsin–Madison · GE HealthCare
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Jul 9, 2026Zongxia Li, Zhongzhi Li, Yucheng Shi +10Long-Horizon Agents Long-Horizon Task Planning
Tencent HY LLM Frontier · University of Maryland, College Park · University of Georgia +5
Learning to Generate Multiple Objects from Dense and Occluded Layouts
Jul 3, 2026Bach-Hoang Ngo, Si-Tri Ngo, Hieu Le +1Diverse Occlusion-And-Revelation Scenarios Scene Reasoning
University of Science, Ho Chi Minh City, Vietnam · 2Vietnam National University, Ho Chi Minh City, Vietnam · 3UNC Charlotte, North Carolina, United States
Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Jul 2, 2026Meng Wang, Haohan Zhao, Wenzhuo Liu +7Unsupervised On-Policy Self-Distillation Replay-Based Continual Learning
Centre for Artificial Intelligence and Robotics, HKISI, CAS · Institute of Automation, CAS · University of Chinese Academy of Sciences +1
Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
Jul 1, 2026Alexander Chemeris, Ming Jin, Randall BalestrieroLatent States Time Series
Langotime South Africa · Griffith University Australia · Brown University United States
CurvSegFlow: Time-Conditioned Flow Matching for Robust Segmentation of Curvilinear Structures in Noisy Biomedical Images
Jun 19, 2026Sidi Mohamed Sid'El Moctar, Achraf Ait Laydi, Alexandre Beber +4Vessel Segmentation Semi-Supervised Medical Image Segmentation
CNRS, Univ. Rennes, Institute of Genetics and Development of Rennes (IGDR), Rennes, France · TIAD Laboratory, Sciences and Technology Faculty, Sultan Moulay Slimane Univ, Beni Mellal, Morocco · Institute of Biotechnology, Czech Academy of Sciences, Vestec, Czech Republic
On the QUEST for Uncertainty Quantification via Highest Density Regions
Jun 17, 2026Sam Goring, Tom Kuipers, Nicola Paoletti +1Uncertainty Quantification Uncertainty
King’s College London · Northeastern University London
Point Cloud Upsampling through Patch-based Frequency Superposition
Jun 12, 2026Marina Ritthaler, Azhar Hussian, Vasileios Belagiannis +1Point Clouds Upsampling
Chair of Multimedia Communications and Signal Processing Friedrich-Alexander-University Erlangen-Nuremberg Erlangen, Germany
LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction
Jun 11, 2026Charles Moslonka, Amaury de Vitry, Arthur Garnier +2Financial Question Answering Report
Artefact Research Center Paris, France · MICS, CentraleSupélec, Université Paris-Saclay Gif-sur-Yvette, France · Ardian Paris, France
The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search
Jun 9, 2026Charith Chandra Sai Balne, Rithwik Maramraju, Siddharth Pratap Singh +4Retrieval Layer Dense
Walmart Global Tech USA · Walmart Global Tech2026 USA
PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments
Jun 8, 2026Minghao Zou, Qingtian Zeng, Shangkun Liu +5Spatio-Temporal Scene Graphs Scene Understanding
Cardiff University Cardiff, UK · Shandong University of Science and Technology Qingdao, China · University of Exeter Exeter, UK +3
HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes
Jun 4, 2026Wenbo Li, Xiaoliang Ju, Zipeng Qin +2Indoor Scene Generation Floor Plan Generation
Ace Robotics · CUHK MMLab · Shenzhen Loop Area Institute
Geometry-Aware Dataset Condensation for Diffusion Model Training
Jun 4, 2026Xiao Cui, Yulei Qin, Mo Zhu +3Diffusion Models Distributional Fidelity
University of Science and Technology of China · Independent Researcher · Zhejiang University +1
DENSER: Depth-Guided Ensemble with Staged EFA-GS Reconstruction for Soccer Novel View Synthesis
May 31, 2026Parthsarthi RawatNovel View Synthesis Scene Reconstruction
GameChanger by Dick’s Sporting Goods
Test-Time Training for Zero-Resource Dense Retrieval Reranking
May 31, 2026Shiyan Liu, Yichen LiRetrieval Layer Cross-Encoder Reranking
Huazhong University of Science and Technology · ByteDance
Building and Road Recognition in Dense Urban Informal Settlements: A Dataset and Benchmark
May 28, 2026Hongyu Long, Jiaxuan Liu, Rui CaoUrban Environments Dense Annotation
UGOD Thrust, HKUST(GZ)
Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
May 22, 2026Guoming Li, Shangyu Zhang, Junwei Pan +7Real-World Content Recommendation Problem Recommendation Quality
The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China · Tencent Inc. Shenzhen, China
Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching
May 13, 2026Abdalrahman WaelMixture-Of-Experts Small Models
Independent Researcher
One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators
May 7, 2026Panos Tsimpos, Edoardo Calvello, Ayoub Belhadji +1Conditional Distribution Probabilistic Operator Learning
Operations Research Center MASSachusetts Institute of Technology Cambridge, MA 02139 · Department of Computing and Mathematical Sciences California Institute of Technology Pasadena, CA 91125 · Laboratory for Information and Decision Systems Center for Computational Science and Engineering MASSachusetts Institute of Technology Cambridge, MA 02139 +2
Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
May 3, 2026Hongkun Pan, Yuwei Wu, Wanyi Hong +8Chart Multimodal Reasoning
Zhejiang University · State Key Lab of CAD&CG, Zhejiang University · HiThink Research
GateMOT: Q-Gated Attention for Dense Object Tracking
Apr 29, 2026Mingjin Lv, Zelin Liu, Feifei Shao +4Multi-Object Tracking Dense
Huazhong University of Science and Technology, Wuhan, China · Zhejiang University, Hangzhou, China · La Trobe University, Melbourne, Australia
SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios
Apr 24, 2026Shozaburo Hirano, Norimichi UkitaMulti-Object Tracking Motion Estimation
Toyota Technological Institute
A Hough transform approach to safety-aware scalar field mapping using Gaussian Processes
Apr 22, 2026Muzaffar Qureshi, Trivikram Satharasi, Tochukwu E. Ogri +2Gaussian Process Scalar Field
Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA · Torch Technologies, Shalimar, Florida, USA
Dynamical stability for dense patterns in attractor neural networks
Jul 14, 2025Uri Cohen, Máté LengyelNeural Circuits Attractors
Computational and Biological Learning Lab, Department of Engineering, University of Cambridge, Cambridge, UK · Center for Cognitive Computation, Department of Cognitive Science, Central European University, Budapest, Hungary
Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval
Date pendingChenyu Wu, You LinRetrieval Layer Dense
Duke University Durham, NC, USA · Independent Researcher New York, NY, USA

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual Density

Xinhe Wu, Yadong Jin

iSoftStone AI Research Lab (ISSAIR) iSoftStone Beijing, China

Dense Multimodal Large Language Models

Open paper AskPDF arXiv

Multimodal large language models (MLLMs) offer a promising approach for recovering numerical data from scientific charts, but their ability to reconstruct chart data from visually dense figures remains poorly understood. Existing chart understanding benchmarks primarily evaluate question answering or chart-level reasoning and provide limited support for evaluating structured numerical reconstruction from scientific figures. We introduce \textbf{ChartDensity-Bench}, a benchmark for evaluating MLLMs on structured numerical data reconstruction from compound chart figures under controlled visual density. Built from charts paired with source-level ground-truth data, ChartDensity-Bench systematically varies the number of simultaneously presented charts (

k\in{1,3,6,9}

), enabling controlled evaluation of density-induced degradation. We further propose a multi-dimensional evaluation framework covering structural reliability, reconstruction completeness, parseability, and numerical fidelity. Experiments on five recent MLLMs show that numerical reconstruction generally degrades as visual density increases, while the magnitude of degradation varies substantially across models. Chart-level paired comparisons further show that the same source chart can incur higher reconstruction error when embedded in denser visual contexts. These findings highlight visual density as an important and previously underexplored factor in MLLM chart data reconstruction and provide a systematic benchmark for evaluating model robustness in this setting.

Momentum

Related topics

Latest papers 45